Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    providedIn
    -0.51
    hObject
    -0.51
    apas
    -0.48
    רוב
    -0.48
     policy
    -0.45
    ponses
    -0.45
     calles
    -0.45
    şen
    -0.44
    mps
    -0.44
     persoons
    -0.43
    POSITIVE LOGITS
    躇
    0.74
     nakalista
    0.71
    енча
    0.67
     LUMP
    0.64
    Liên
    0.62
     חיצוניים
    0.60
    曖昧さ回避
    0.60
     ujednoznacz
    0.60
     Boi
    0.59
    MemoryWarning
    0.59
    Act Density 1.737%

    No Known Activations